← 返回 Skills 市场
Meta Ai
作者
vynbosserman65
· GitHub ↗
· v1.0.0
· MIT-0
76
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install meta-ai
功能描述
content creators enhance video clips into AI-edited videos using this skill. Accepts MP4, MOV, AVI, WebM up to 500MB, renders on cloud GPUs at 1080p, and ret...
安全使用建议
This skill appears to do what it says (cloud video enhancement) and only needs a single service token. However: 1) the package has no homepage or verifiable source — verify the domain (mega-api-prod.nemovideo.ai) and the provider before sending sensitive video content; 2) the skill will auto-create and store an anonymous token if you don't set NEMO_TOKEN — if you prefer control, set your own NEMO_TOKEN or decline anonymous auth; 3) it may read install/config paths (~/.config/nemovideo/, ~/.clawhub/, ~/.cursor/skills/) for attribution headers — consider whether you want the agent to access those paths; 4) because this skill uploads/processes video on a third‑party cloud, avoid sending videos with sensitive PII unless you trust the service. If you want higher assurance, ask the publisher for a homepage, privacy policy, and API provenance before using.
功能分析
Type: OpenClaw Skill
Name: meta-ai
Version: 1.0.0
The skill facilitates video editing via a third-party API (mega-api-prod.nemovideo.ai) but exhibits several high-risk behaviors in SKILL.md. It requires access to environment variables (NEMO_TOKEN) and local configuration directories (~/.config/nemovideo/), and it instructs the AI agent to automatically initiate network connections and generate anonymous tokens without explicit user consent. Most notably, it contains instructions to hide raw API responses and token values from the user, which reduces transparency and could mask unauthorized data transmission or session manipulation.
能力评估
Purpose & Capability
The name/description (AI-assisted video editing) match the instructions (upload, session, render, export). Requiring a single service token (NEMO_TOKEN) is appropriate. Minor inconsistency: registry metadata at the top stated no required config paths, but the SKILL.md frontmatter and runtime instructions reference ~/.config/nemovideo/ and reading the YAML frontmatter for X-Skill-Source/Version/Platform.
Instruction Scope
Runtime instructions stay within the editing workflow: create/refresh an anonymous token if NEMO_TOKEN is absent, create sessions, upload files, stream SSE edits, poll renders, and return download URLs. They also instruct reading the skill's YAML frontmatter and detecting install path (~/.clawhub or ~/.cursor/skills) to set an X-Skill-Platform header — reading those paths is not strictly required for core editing but is plausible for attribution. Instructions explicitly tell the agent not to display raw API responses or token values, and to store session_id/token for subsequent calls.
Install Mechanism
No install spec and no code files (instruction-only). This is the lowest-risk install surface — nothing is downloaded or written by the skill itself per the manifest.
Credentials
Only one credential is declared (NEMO_TOKEN), which is proportionate to a backend API. The skill also implements an anonymous-token flow if the env var is missing (generates a client UUID and posts to the service). The earlier registry metadata omission of config paths vs the frontmatter declaration is inconsistent but not necessarily malicious.
Persistence & Privilege
always is false and the skill does not request system-wide changes or additional privileges. Autonomous invocation is allowed by default but is not combined with broad or unrelated credential access.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install meta-ai - 安装完成后，直接呼叫该 Skill 的名称或使用
/meta-ai触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Meta AI — AI-Assisted Video Editing Tool v1.0.0
- Initial release: AI-powered video editing and enhancement for content creators.
- Supports MP4, MOV, AVI, and WebM uploads up to 500MB; outputs 1080p MP4 in 30–60 seconds via cloud GPU rendering.
- Automatic session and authentication setup with free credits (100, valid 7 days).
- Handles common workflows: quick enhancement, batch processing, iterative edits, and timeline previews.
- Integrates Meta AI backend features: credits check, export, file upload, and live session updates.
- Robust error handling for authentication, file limits, and process state.
元数据
常见问题
Meta Ai 是什么？
content creators enhance video clips into AI-edited videos using this skill. Accepts MP4, MOV, AVI, WebM up to 500MB, renders on cloud GPUs at 1080p, and ret... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 76 次。
如何安装 Meta Ai？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install meta-ai」即可一键安装，无需额外配置。
Meta Ai 是免费的吗？
是的，Meta Ai 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Meta Ai 支持哪些平台？
Meta Ai 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Meta Ai？
由 vynbosserman65（@vynbosserman65）开发并维护，当前版本 v1.0.0。
推荐 Skills